{"id":"https://openalex.org/W4404056518","doi":"https://doi.org/10.1109/tase.2024.3487219","title":"Hierarchical Reinforcement Learning for Swarm Confrontation With High Uncertainty","display_name":"Hierarchical Reinforcement Learning for Swarm Confrontation With High Uncertainty","publication_year":2024,"publication_date":"2024-11-05","ids":{"openalex":"https://openalex.org/W4404056518","doi":"https://doi.org/10.1109/tase.2024.3487219"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2024.3487219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3487219","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108616249","display_name":"Qizhen Wu","orcid":"https://orcid.org/0009-0004-5819-1230"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qizhen Wu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451446","display_name":"Kexin Liu","orcid":"https://orcid.org/0000-0003-4328-6339"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexin Liu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4328-6339","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-1859-384X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Advanced Research Institute of Multidisciplinary Sciences and the State Key Laboratory of CNS/ATM, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1859-384X","affiliations":[{"raw_affiliation_string":"Advanced Research Institute of Multidisciplinary Sciences and the State Key Laboratory of CNS/ATM, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027725400","display_name":"Jinhu L\u00fc","orcid":"https://orcid.org/0000-0003-0275-8387"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhu L\u00fc","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0275-8387","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8408,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91556707,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"8630","last_page":"8644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.961899995803833,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.961899995803833,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9617999792098999,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10482","display_name":"Mathematical and Theoretical Epidemiology and Ecology Models","score":0.9264000058174133,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7322249412536621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.533380389213562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5160893797874451},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4203140139579773},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3335638642311096},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.32452988624572754},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.0838460624217987}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7322249412536621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.533380389213562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160893797874451},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4203140139579773},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3335638642311096},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.32452988624572754},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0838460624217987}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2024.3487219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3487219","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2575069074","display_name":null,"funder_award_id":"62088101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3140767831","display_name":null,"funder_award_id":"2022YFB3305600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G561250190","display_name":null,"funder_award_id":"62141604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7506325451","display_name":null,"funder_award_id":"62003015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W3033315161","https://openalex.org/W3093345403","https://openalex.org/W3112680002","https://openalex.org/W3145159167","https://openalex.org/W3185921569","https://openalex.org/W3205656755","https://openalex.org/W3214814008","https://openalex.org/W4200512239","https://openalex.org/W4207021923","https://openalex.org/W4226076794","https://openalex.org/W4226270887","https://openalex.org/W4226362429","https://openalex.org/W4283262646","https://openalex.org/W4287884191","https://openalex.org/W4289821409","https://openalex.org/W4312130767","https://openalex.org/W4313072676","https://openalex.org/W4317038451","https://openalex.org/W4319996426","https://openalex.org/W4321763414","https://openalex.org/W4322730949","https://openalex.org/W4323075742","https://openalex.org/W4380520220","https://openalex.org/W4386285856","https://openalex.org/W4387526302","https://openalex.org/W4388904831","https://openalex.org/W4390204350","https://openalex.org/W4391640441","https://openalex.org/W4392108144","https://openalex.org/W4392406041","https://openalex.org/W4392843802","https://openalex.org/W4394674699","https://openalex.org/W4396730906","https://openalex.org/W6734215269","https://openalex.org/W6751494529","https://openalex.org/W6753264383","https://openalex.org/W6764053384","https://openalex.org/W6803753956","https://openalex.org/W6846930601"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0,170],"swarm":[1,42,212,227],"robotics,":[2],"confrontation":[3,43,313],"including":[4,140],"the":[5,25,34,58,81,87,92,97,114,118,125,131,146,161,179,183,208,211,226,245,266,270,274,281,286,291,294,312],"pursuit-evasion":[6],"game":[7],"is":[8,39,232,302],"a":[9,29,64,72,76,108,204,240,303,328],"key":[10],"scenario.":[11],"High":[12],"uncertainty":[13,115,267],"caused":[14,268],"by":[15,130,214,269],"unknown":[16],"opponents\u2019":[17],"strategies,":[18],"dynamic":[19,83],"obstacles,":[20],"and":[21,80,103,116,142,149,157,163,222,273,300,325],"insufficient":[22],"training":[23,127,138,147],"complicates":[24],"action":[26],"space":[27],"into":[28,100,228],"hybrid":[30,59,98,304],"decision":[31,295],"process.":[32,60],"Although":[33],"deep":[35],"reinforcement":[36,67,236],"learning":[37,68,237],"method":[38,139,185,238],"significant":[40,205],"for":[41,280],"since":[44],"it":[45,54],"can":[46],"handle":[47],"various":[48],"sizes,":[49],"as":[50],"an":[51,136],"end-to\u2013end":[52],"implementation,":[53],"cannot":[55,307],"deal":[56],"with":[57,107,174,298],"Here,":[61],"we":[62,134,263,289],"propose":[63],"novel":[65],"hierarchical":[66],"approach":[69],"consisting":[70],"of":[71,166,182,247,283,314],"target":[73],"allocation":[74,102],"layer,":[75,79],"path":[77],"planning":[78,105],"underlying":[82],"interaction":[84,119],"mechanism":[85],"between":[86],"two":[88,132],"layers,":[89,106,133],"which":[90,144,276,306],"indicates":[91],"quantified":[93],"uncertainty.":[94],"It":[95],"decouples":[96],"process":[99,128,296],"discrete":[101],"continuous":[104],"probabilistic":[109],"ensemble":[110],"model":[111],"to":[112,123,176,195,243,257,330],"quantify":[113],"regulate":[117],"frequency":[120],"adaptively.":[121],"Furthermore,":[122],"overcome":[124],"unstable":[126],"introduced":[129],"design":[135],"integration":[137],"pre-training":[141],"cross-training,":[143],"enhances":[145],"efficiency":[148],"stability.":[150],"Experiment":[151],"results":[152],"in":[153,207,220,311],"both":[154],"comparison,":[155],"ablation,":[156],"real-robot":[158],"studies":[159],"validate":[160],"effectiveness":[162],"generalization":[164],"performance":[165],"our":[167,171,278,317],"proposed":[168,184],"approach.":[169],"defined":[172],"experiments":[173],"twenty":[175],"forty":[177],"agents,":[178],"win":[180],"rate":[181],"reaches":[186],"around":[187],"ninety":[188],"percent,":[189],"outperforming":[190],"other":[191,287],"traditional":[192],"methods.":[193],"Note":[194],"Practitioners\u2014With":[196],"artificial":[197,322],"intelligence":[198,324],"rapidly":[199],"developing,":[200],"robots":[201,216],"will":[202],"play":[203],"role":[206],"future.":[209],"Especially,":[210],"formed":[213],"many":[215],"holds":[217],"promising":[218],"potential":[219],"civil":[221],"military":[223],"applications.":[224],"Promoting":[225],"games":[229],"or":[230],"battles":[231],"rather":[233],"riveting.":[234],"The":[235],"provides":[239],"plausible":[241],"solution":[242,329],"realize":[244],"battle":[246],"robotic":[248],"swarms.":[249,284,315],"There":[250],"are":[251],"still":[252],"some":[253],"issues":[254],"that":[255,293],"need":[256],"be":[258,308],"addressed.":[259],"On":[260,285],"one":[261],"hand,":[262,288],"focus":[264],"on":[265,321],"battlefield":[271],"nature":[272],"environment":[275],"limits":[277],"ability":[279],"implementation":[282],"solve":[290],"problem":[292],"combined":[297],"commands":[299],"actions":[301],"system,":[305],"directly":[309],"reflected":[310],"Overall,":[316],"approaches":[318],"throw":[319],"light":[320],"general":[323],"also":[326],"reveal":[327],"interpretable":[331],"intelligence.":[332]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}